Montreal, Québec, Canada

Roberto Rocha

Data storyteller and educator

Menu
  • Home
  • CV
  • Blog
  • Data services
  • Training
  • Contact

GPT-3

image image-1

Getting tabular data from unstructured text with GPT-3: an ongoing experiment

October 4, 2022October 24, 2022 Roberto 10 Comments

One of the most exciting applications of AI in journalism is the creation of structured data from unstructured text. Government reports, legal documents, emails, memos… these are rich with content like names, organizations, dates, and prices. But to get them into a format that can be analyzed and counted, like a spreadsheet, usually involves days […]

Posted in Data Journalism Tags AI, GPT-3, lobbying, NLP
Read More

Recent Posts

  • Pair programming with LLMs: putting 5 leading models to the test
  • How to use ChatGPT Vision to turn handwritten forms into data
  • Using ChatGPT to clean data: an experiment
  • How to extract entities from raw text with Spacy: 3 approaches using Canadian data
  • Getting tabular data from unstructured text with GPT-3: an ongoing experiment

Recent Comments

  • Aditya Sharma on Using Python’s calendar module for scraping date-based data
  • Jed Clark on Using NLP to analyze open-ended responses in surveys
  • Roberto on Using ChatGPT to clean data: an experiment
  • Chris on Using ChatGPT to clean data: an experiment
  • Jacques Dufort on Using NLP to analyze open-ended responses in surveys
Theme: Albar by Kaira